Interpretable compositional computation with recurrent neural networks
Flexible cognition utilizes reusable components to enable rapid adaptation of behavior to different contexts or tasks. Analysis of artificial neural networks trained on multiple tasks suggested that this compositionality is supported by dynamical structures which are shared and re-used across tasks. However, the nature of these shared components, and how they can be used in a task-dependent manner, remained unclear. Here, we develop a theory of interpretable compositional computation based on shared dynamical structures in the low-dimensional latent space of low-rank recurrent neural networks. We show that these shared latent components are not immediately visible in the neural activity, and are thus compatible with task-dependent activity. We identify hallmarks of shared latent components both in the connectivity statistics and the neural representations. These hallmarks yield testable predictions for the networks response to specific perturbation experiments. Finally, we identify distinct loci where task-dependence can enter the computation, allowing us to characterize qualitatively different solutions to compositional tasks. In summary, our theory provides a mechanistic understanding and testable hallmarks of compositional computation via shared components in low-rank networks.